Method, apparatus, device, storage medium and program product for video generating

Abstract

The present disclosure relates to a video generating method and apparatus, a device, a storage medium and a program product. The method comprises: acquiring first text information, wherein the first text information is used for describing writing requirements of a video copywriting; generating second text information based on the first text information, wherein the second text information is copywriting information meeting the writing requirements described by the first text information; generating multimedia editing data based on third text information; generating a target video based on the multimedia editing data. Embodiments of the present disclosure provide an efficient one-stop video production scheme, and improve video production efficiency by generating copywriting information meeting the described writing requirements based on the writing requirements describing the video copywriting, and then producing the video according to the generated copywriting information.

I/We claim: 
     
         1 . A video generating method, wherein the method comprises:
 acquiring first information, wherein the first information is used for describing writing requirements of a video copywriting;   generating second information based on the first information, wherein the second information is copywriting information based on the first information;   generating multimedia editing data based on the second information; wherein the multimedia editing data comprises at least one video editing track segment that respectively corresponds to at least one information segment divided based on the second information; and   generating a target video based on the multimedia editing data.   
     
     
         2 . The method of  claim 1 , wherein generating second information based on the first information comprises:
 generating at least one of candidate copywriting information based on the first information;   switching to present different candidate copywriting information of the at least one of candidate copywriting information in a copywriting input interface in response to a switching operation triggered by a user;   determining, in response to a confirmation operation triggered by the user, candidate copywriting information which is among the at least one of candidate copywriting information and is switched to be presented in the copywriting input interface, as the second information.   
     
     
         3 . The method of  claim 2 , wherein the copywriting input interface has a copywriting input area and a candidate copywriting area therein;
 the copywriting input interface has a copywriting switching control in, and the copywriting switching control is used for triggering the switching operation to switch to present different candidate copywriting information of the at least one of candidate copywriting information in the candidate copywriting area;   the copywriting input interface has a copywriting confirmation control, and the copywriting confirmation control is used for triggering the confirmation operation to determine candidate copywriting information presented in the candidate copywriting area as the second information and present the second information in the copywriting input area.   
     
     
         4 . The method of  claim 3 , wherein after the at least one of candidate copywriting information is generated, the candidate copywriting information presented by the candidate copywriting area is inserted at a user input position in the copywriting input area;
 in response to the confirmation operation, the candidate copywriting area is deleted from the copywriting input area.   
     
     
         5 . The method of  claim 4 , wherein in response to fourth information is present in the copywriting input area before the at least one candidate copywriting information is generated, fifth information generated by fusing the second information with the fourth information is present in the input area after the second information is determined. 
     
     
         6 . The method of  claim 5 , wherein in response to the user input position is located at a middle position of the fourth information, in the input area the fourth information is cut by the candidate copywriting area from the middle position and presented on both sides of the candidate copywriting area, and the second information in the fifth information is inserted at the middle position of the fourth information. 
     
     
         7 . The method of  claim 5 , wherein the method further comprises:
 editing the fifth information to obtain third information in response to the user's input operation;   generating the multimedia editing data based on the second information further comprises:
 obtain the third information based on the second information; 
   wherein the multimedia editing data further comprises at least one audio editing track segment; and wherein the at least one video editing track segment and the at least one audio editing track segment respectively correspond to at least one segment divided from the third information; and   wherein a target audio editing track segment of the at least one audio editing track segment is used to fill a read speech matching the target segment, and a target video editing track in the at least one video editing track segment and the target audio editing track segment occupy the same timeline position on a video editing timeline.   
     
     
         8 . The method of  claim 2 , wherein the method further comprises:
 determining a target copywriting category from a plurality of copywriting categories; the candidate copywriting information is generated based on the target copywriting category and the first information, and the copywriting category of the second information is the target copywriting category.   
     
     
         9 . The method of  claim 8 , wherein the copywriting input interface has a first copywriting category control and a second copywriting category control, wherein the first copywriting category control is used for taking a copywriting category corresponding to the first copywriting category control as a target copywriting category in response to a triggering operation of the user; and the second copywriting category control is used for taking a copywriting category corresponding to the second copywriting category control as the target copywriting category in response to a triggering operation of the user. 
     
     
         10 . The method of  claim 1 , wherein the target video segment is an empty segment; or
 the target video segment is used to fill a video image matching the target segment; or   the target video segment is used to fill a meme image matching the target segment.   
     
     
         11 . An electronic device, wherein the electronic device comprises:
 at least one processor;   a storage device for storing at least one program;   the at least one program, when executed by the at least one processor, causes the at least one processor to:   acquire first information, wherein the first information is used for describing writing requirements of a video copywriting;   generate second information based on the first information, wherein the second information is copywriting information based on the first information;   generate multimedia editing data based on the second information; wherein the multimedia editing data comprises at least one video editing track segment that respectively corresponds to at least one information segment divided based on the second information; and   generate a target video based on the multimedia editing data.   
     
     
         12 . The electronic device of  claim 11 , wherein the processor is further caused to:
 generate at least one of candidate copywriting information based on the first information;   switch to present different candidate copywriting information of the at least one of candidate copywriting information in a copywriting input interface in response to a switching operation triggered by a user;   determining, in response to a confirmation operation triggered by the user, candidate copywriting information which is among the at least one of candidate copywriting information and is switched to be presented in the copywriting input interface, as the second information.   
     
     
         13 . The electronic device of  claim 12 , wherein the copywriting input interface has a copywriting input area and a candidate copywriting area therein;
 the copywriting input interface has a copywriting switching control in, and the copywriting switching control is used for triggering the switching operation to switch to present different candidate copywriting information of the at least one of candidate copywriting information in the candidate copywriting area;   the copywriting input interface has a copywriting confirmation control, and the copywriting confirmation control is used for triggering the confirmation operation to determine candidate copywriting information presented in the candidate copywriting area as the second information and present the second information in the copywriting input area.   
     
     
         14 . The electronic device of  claim 13 , wherein after the at least one of candidate copywriting information is generated, the candidate copywriting information presented by the candidate copywriting area is inserted at a user input position in the copywriting input area;
 in response to the confirmation operation, the candidate copywriting area is deleted from the copywriting input area.   
     
     
         15 . The electronic device of  claim 14 , wherein in response to fourth information is present in the copywriting input area before the at least one candidate copywriting information is generated, fifth information generated by fusing the second information with the fourth information is present in the input area after the second information is determined. 
     
     
         16 . The electronic device of  claim 15 , wherein in response to the user input position is located at a middle position of the fourth information, in the input area the fourth information is cut by the candidate copywriting area from the middle position and presented on both sides of the candidate copywriting area, and the second information in the fifth information is inserted at the middle position of the fourth information. 
     
     
         17 . The electronic device of  claim 15 , wherein the processor is further caused to:
 edit the fifth information to obtain third information in response to the user's input operation;   generate the multimedia editing data based on the second information by obtaining the third information based on the second information;   wherein the multimedia editing data further comprises at least one audio editing track segment, and wherein the at least one video editing track segment and the at least one audio editing track segment respectively correspond to at least one segment divided from the third information; and   wherein a target audio editing track segment of the at least one audio editing track segment is used to fill a read speech matching the target segment, and a target video editing track in the at least one video editing track segment and the target audio editing track segment occupy the same timeline position on a video editing timeline.   
     
     
         18 . The electronic device of  claim 12 , wherein the processor is further caused to:
 determine a target copywriting category from a plurality of copywriting categories; the candidate copywriting information is generated based on the target copywriting category and the first information, and the copywriting category of the second information is the target copywriting category.   
     
     
         19 . A computer program product, stored on a non-transitory computer storage medium, comprising computer program or instructions which, when executed by a processor, causes the processor to:
 acquire first information, wherein the first information is used for describing writing requirements of a video copywriting;   generate second information based on the first information, wherein the second information is copywriting information based on the first information;   generate multimedia editing data based on the second information; wherein the multimedia editing data comprises at least one video editing track segment that respectively corresponds to at least one information segment divided based on the second information; and   generate a target video based on the multimedia editing data.   
     
     
         20 . The product of  claim 19 , wherein the processor is further caused to generate the multimedia editing data based on the second information by:
 obtaining the third information based on the second information;   wherein the multimedia editing data further comprises at least one audio editing track segment; wherein the at least one video editing track segment and the at least one audio editing track segment respectively correspond to at least one segment divided from the third information; and   wherein a target audio editing track segment of the at least one audio editing track segment is used to fill a read speech matching the target segment, and a target video editing track in the at least one video editing track segment and the target audio editing track segment occupy the same timeline position on a video editing timeline.